Computational efficiency and non-adversarial robustness are critical factors in process modeling and optimization for real-world engineering applications. Yet, conventional neural networks often fall short in addressing both simultaneously, or even separately. Drawing insights from natural physical systems and existing literature, it is known theoretically that an input convex architecture will enhance computational efficiency, while a Lipschitz-constrained architecture will bolster non-adversarial robustness. However, integrating both properties into one model is a nontrivial task, as enforcing one property may compromise the other one. Therefore, in this work, we develop a novel network architecture, termed Input Convex Lipschitz Recurrent Neural Networks, that inherits the strengths of both convexity and Lipschitz continuity. This model is explicitly designed for fast and robust optimization-based tasks, which outperforms existing recurrent units in terms of computational efficiency and non-adversarial robustness. Additionally, we have successfully implemented this model in various practical engineering applications, such as optimization of chemical processes and real-world solar irradiance prediction for Solar PV system planning at LHT Holdings in Singapore. Source code is available at https://github.com/killingbear999/ICLRNN.

翻译：计算效率与非对抗鲁棒性是实际工程应用中过程建模与优化的关键因素。然而，传统神经网络往往难以同时满足这两项要求，甚至难以分别实现。借鉴自然物理系统与现有文献的理论成果可知，输入凸架构理论上可提升计算效率，而利普希茨约束架构则能增强非对抗鲁棒性。但将两种特性集成至单一模型并非易事，因为强化一种特性可能削弱另一种特性。为此，本研究提出了一种新型网络架构——输入凸利普希茨循环神经网络（Input Convex Lipschitz Recurrent Neural Networks, ICLRNN），该架构兼具凸性与利普希茨连续性的优势。本模型专为基于优化的快速稳健任务而设计，在计算效率与非对抗鲁棒性方面均优于现有循环单元。此外，我们已将该模型成功应用于多项实际工程场景，包括新加坡LHT Holdings公司光伏系统规划中的化工过程优化与真实太阳辐照度预测。源代码详见 https://github.com/killingbear999/ICLRNN。